当前位置: X-MOL 学术Integr. Comput. Aided Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A spectrum-domain instance segmentation model for casting defects
Integrated Computer-Aided Engineering ( IF 5.8 ) Pub Date : 2021-09-17 , DOI: 10.3233/ica-210666
Jinhua Lin 1, 2 , Lin Ma 3 , Yu Yao 1
Affiliation  

Accurate segmentation of casting defects plays a positive role in the quality control of casting products, and is of great significance for accurate extraction of the mechanical properties of defects in the casting solidification process. However, as the shape of casting defects is complex and irregular, it is challenging to segment casting defects by existing segmentation methods. To address this, a spectrum domain instance segmentation model (SISN) is proposed for segmenting five types of casting defects with complex shapes accurately. The five defects are inclusion, shrinkage, hot tearing, cold tearing and micro pore. The proposed model consists of three sub-models: the spectrum domain region proposal model (SRPN), spectrum domain region of interest alignment model (SRoIAlign) and spectrum domain instance generation model (SIGN). SRPN uses a multi-scale anchoring mechanism to detect defects of various sizes, where the SSReLU and SCPool functions are used to solve the spectrum domain gradient explosion problem and the spectrum domain over-fitting problem. SRoIAlign uses the floating-point quantization operation and the tri-linear interpolation method to quantize the 3D proposals to the feature values in an accurate manner. SIGN is a full-spectrum domain neural network applied to 3D proposals, generating a segmentation instance of defects in a point-wise manner. In the experiments, we test the effectiveness of the proposed model from three aspects: segmentation accuracy, time performance and mechanical property extraction accuracy.

中文翻译:

一种铸造缺陷的谱域实例分割模型

铸件缺陷的准确分割对于铸件产品的质量控制具有积极的作用,对于准确提取铸件凝固过程中缺陷的力学性能具有重要意义。然而,由于铸造缺陷的形状复杂且不规则,现有的分割方法对铸造缺陷进行分割具有挑战性。为了解决这个问题,提出了一种频谱域实例分割模型(SISN),用于准确分割五种形状复杂的铸造缺陷。五种缺陷是夹杂物、收缩、热撕裂、冷撕裂和微孔。所提出的模型由三个子模型组成:频谱域区域提议模型(SRPN)、频谱域感兴趣区域对齐模型(SRoIAlign)和频谱域实例生成模型(SIGN)。SRPN采用多尺度锚定机制检测各种尺寸的缺陷,其中SSReLU和SCPool函数用于解决谱域梯度爆炸问题和谱域过拟合问题。SRoIAlign 使用浮点量化操作和三线性插值方法将 3D 建议以准确的方式量化为特征值。SIGN 是一种应用于 3D 建议的全谱域神经网络,以逐点方式生成缺陷的分割实例。在实验中,我们从分割精度、时间性能和力学性能提取精度三个方面测试了所提出模型的有效性。其中SSReLU和SCPool函数用于解决谱域梯度爆炸问题和谱域过拟合问题。SRoIAlign 使用浮点量化操作和三线性插值方法将 3D 建议以准确的方式量化为特征值。SIGN 是一种应用于 3D 建议的全谱域神经网络,以逐点方式生成缺陷的分割实例。在实验中,我们从分割精度、时间性能和力学性能提取精度三个方面测试了所提出模型的有效性。其中SSReLU和SCPool函数用于解决谱域梯度爆炸问题和谱域过拟合问题。SRoIAlign 使用浮点量化操作和三线性插值方法将 3D 建议以准确的方式量化为特征值。SIGN 是一种应用于 3D 建议的全谱域神经网络,以逐点方式生成缺陷的分割实例。在实验中,我们从分割精度、时间性能和力学性能提取精度三个方面测试了所提出模型的有效性。SRoIAlign 使用浮点量化操作和三线性插值方法将 3D 建议以准确的方式量化为特征值。SIGN 是一种应用于 3D 建议的全谱域神经网络,以逐点方式生成缺陷的分割实例。在实验中,我们从分割精度、时间性能和力学性能提取精度三个方面测试了所提出模型的有效性。SRoIAlign 使用浮点量化操作和三线性插值方法将 3D 建议以准确的方式量化为特征值。SIGN 是一种应用于 3D 建议的全谱域神经网络,以逐点方式生成缺陷的分割实例。在实验中,我们从分割精度、时间性能和力学性能提取精度三个方面测试了所提出模型的有效性。
更新日期:2021-09-17
down
wechat
bug